© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13918
    Prev
    Next
    INDEX
    Explanations

    contrast or alternative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ultraf
    0.75
     they
    0.70
     lige
    0.66
     फोर्थ
    0.64
    しないで
    0.63
     dramatic
    0.63
     honorary
    0.63
     ));
    0.61
     THEY
    0.61
     ...");
    0.61
    POSITIVE LOGITS
     More
    1.14
    More
    1.13
     plutôt
    1.06
     more
    0.98
     Más
    0.97
    more
    0.96
     sondern
    0.94
    Rather
    0.92
     rather
    0.91
    Instead
    0.90
    Activations Density 0.033%

    No Known Activations